Development of a Tremor Detection Algorithm for Use in an Academic Movement Disorders Center
Mark Saad,
Sofia Hefner,
Suzann Donovan,
Doug Bernhard,
Richa Tripathi,
Stewart A. Factor,
Jeanne M. Powell,
Hyeokhyen Kwon,
Reza Sameni,
Christine D. Esper,
J. Lucas McKay
Affiliations
Mark Saad
Jean and Paul Amos Parkinson’s Disease and Movement Disorders Program, Department of Neurology, School of Medicine, Emory University, Atlanta, GA 30322, USA
Sofia Hefner
Department of Neuroscience, Georgia Institute of Technology, Atlanta, GA 30322, USA
Suzann Donovan
Department of Neuroscience and Behavioral Biology, College of Arts and Sciences, Emory University, Atlanta, GA 30322, USA
Doug Bernhard
Jean and Paul Amos Parkinson’s Disease and Movement Disorders Program, Department of Neurology, School of Medicine, Emory University, Atlanta, GA 30322, USA
Richa Tripathi
Jean and Paul Amos Parkinson’s Disease and Movement Disorders Program, Department of Neurology, School of Medicine, Emory University, Atlanta, GA 30322, USA
Stewart A. Factor
Jean and Paul Amos Parkinson’s Disease and Movement Disorders Program, Department of Neurology, School of Medicine, Emory University, Atlanta, GA 30322, USA
Jeanne M. Powell
Department of Psychology, Laney Graduate School, Emory University, Atlanta, GA 30322, USA
Hyeokhyen Kwon
Department of Biomedical Informatics, School of Medicine, Emory University, Atlanta, GA 30322, USA
Reza Sameni
Department of Biomedical Informatics, School of Medicine, Emory University, Atlanta, GA 30322, USA
Christine D. Esper
Jean and Paul Amos Parkinson’s Disease and Movement Disorders Program, Department of Neurology, School of Medicine, Emory University, Atlanta, GA 30322, USA
J. Lucas McKay
Jean and Paul Amos Parkinson’s Disease and Movement Disorders Program, Department of Neurology, School of Medicine, Emory University, Atlanta, GA 30322, USA
Tremor, defined as an “involuntary, rhythmic, oscillatory movement of a body part”, is a key feature of many neurological conditions including Parkinson’s disease and essential tremor. Clinical assessment continues to be performed by visual observation with quantification on clinical scales. Methodologies for objectively quantifying tremor are promising but remain non-standardized across centers. Our center performs full-body behavioral testing with 3D motion capture for clinical and research purposes in patients with Parkinson’s disease, essential tremor, and other conditions. The objective of this study was to assess the ability of several candidate processing pipelines to identify the presence or absence of tremor in kinematic data from patients with confirmed movement disorders and compare them to expert ratings from movement disorders specialists. We curated a database of 2272 separate kinematic data recordings from our center, each of which was contemporaneously annotated as tremor present or absent by a movement physician. We compared the ability of six separate processing pipelines to recreate clinician ratings based on F1 score, in addition to accuracy, precision, and recall. The performance across algorithms was generally comparable. The average F1 score was 0.84±0.02 (mean ± SD; range 0.81–0.87). The second highest performing algorithm (cross-validated F1=0.87) was a hybrid that used engineered features adapted from an algorithm in longstanding clinical use with a modern Support Vector Machine classifier. Taken together, our results suggest the potential to update legacy clinical decision support systems to incorporate modern machine learning classifiers to create better-performing tools.
